© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2460
    Prev
    Next
    INDEX
    Explanations

    Code/programming text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.54
     Dede
    -0.50
     domes
    -0.50
     zeichnet
    -0.49
     Hadley
    -0.48
     وتسجيلات
    -0.48
    XmlType
    -0.48
     AppModule
    -0.48
     caret
    -0.47
     Creta
    -0.47
    POSITIVE LOGITS
    MENAFN
    0.60
    tvguidetime
    0.58
    ContentAsync
    0.55
    quesa
    0.54
    pielen
    0.52
     tional
    0.52
     שוליים
    0.52
     funcionales
    0.51
    ActionButton
    0.51
    tional
    0.50
    Activations Density 0.001%

    No Known Activations